ta
TanStack
OSS
ta
Pipelines
Nx runs
Insights
Compare tasks
Analytics
Sign in
Toggle Sidebar
ai
ai
Pipelines
fix(ai-gemini): include thinking tokens in completionTokens (#1970) Gemini reports thoughtsTokenCount apart from candidatesTokenCount but bills both as output, so completionTokens undercounted for thinking models. Match openai-base, where completion tokens include reasoning and reasoningTokens is the detail. Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com> Co-authored-by: Alem Tuzlak <t.zlak@hotmail.com>
nx run-many --targets=build --exclude=examples/**,testing/**
⌘K
fix(ai-gemini): include thinking tokens in completionTokens (#1970)
Succeeded
in
6s
Started
Linux
4 CPU cores
read
access token used
Copy command
nx run-many --targets=build --exclude=examples/**,testing/**
1899
820a110
GitHub
Open on GitHub
Tasks
Resource Usage
ta
TanStack
OSS